@inproceedings{wu-etal-2022-using,
title = "Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation",
author = "Wu, Yaru and
Suchanek, Fabian and
Vasilescu, Ioana and
Lamel, Lori and
Adda-Decker, Martine",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.113/",
pages = "1054--1060",
abstract = "Speech characteristics vary from speaker to speaker. While some variation phenomena are due to the overall communication setting, others are due to diastratic factors such as gender, provenance, age, and social background. The analysis of these factors, although relevant for both linguistic and speech technology communities, is hampered by the need to annotate existing corpora or to recruit, categorise, and record volunteers as a function of targeted profiles. This paper presents a methodology that uses a knowledge base to provide speaker-specific information. This can facilitate the enrichment of existing corpora with new annotations extracted from the knowledge base. The method also helps the large scale analysis by automatically extracting instances of speech variation to correlate with diastratic features. We apply our method to an over 120-hour corpus of broadcast speech in French and investigate variation patterns linked to reduction phenomena and/or specific to connected speech such as disfluencies. We find significant differences in speech rate, the use of filler words, and the rate of non-canonical realisations of frequent segments as a function of different professional categories and age groups."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-using">
<titleInfo>
<title>Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaru</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Suchanek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Vasilescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lori</namePart>
<namePart type="family">Lamel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martine</namePart>
<namePart type="family">Adda-Decker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech characteristics vary from speaker to speaker. While some variation phenomena are due to the overall communication setting, others are due to diastratic factors such as gender, provenance, age, and social background. The analysis of these factors, although relevant for both linguistic and speech technology communities, is hampered by the need to annotate existing corpora or to recruit, categorise, and record volunteers as a function of targeted profiles. This paper presents a methodology that uses a knowledge base to provide speaker-specific information. This can facilitate the enrichment of existing corpora with new annotations extracted from the knowledge base. The method also helps the large scale analysis by automatically extracting instances of speech variation to correlate with diastratic features. We apply our method to an over 120-hour corpus of broadcast speech in French and investigate variation patterns linked to reduction phenomena and/or specific to connected speech such as disfluencies. We find significant differences in speech rate, the use of filler words, and the rate of non-canonical realisations of frequent segments as a function of different professional categories and age groups.</abstract>
<identifier type="citekey">wu-etal-2022-using</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.113/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1054</start>
<end>1060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation
%A Wu, Yaru
%A Suchanek, Fabian
%A Vasilescu, Ioana
%A Lamel, Lori
%A Adda-Decker, Martine
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F wu-etal-2022-using
%X Speech characteristics vary from speaker to speaker. While some variation phenomena are due to the overall communication setting, others are due to diastratic factors such as gender, provenance, age, and social background. The analysis of these factors, although relevant for both linguistic and speech technology communities, is hampered by the need to annotate existing corpora or to recruit, categorise, and record volunteers as a function of targeted profiles. This paper presents a methodology that uses a knowledge base to provide speaker-specific information. This can facilitate the enrichment of existing corpora with new annotations extracted from the knowledge base. The method also helps the large scale analysis by automatically extracting instances of speech variation to correlate with diastratic features. We apply our method to an over 120-hour corpus of broadcast speech in French and investigate variation patterns linked to reduction phenomena and/or specific to connected speech such as disfluencies. We find significant differences in speech rate, the use of filler words, and the rate of non-canonical realisations of frequent segments as a function of different professional categories and age groups.
%U https://aclanthology.org/2022.lrec-1.113/
%P 1054-1060
Markdown (Informal)
[Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation](https://aclanthology.org/2022.lrec-1.113/) (Wu et al., LREC 2022)
ACL